Vehicle control method, device, equipment, medium and product based on road section risk detection

Abstract

The present disclosure provides a vehicle control method and device, electronic device, medium and product based on road section risk detection. The method includes: determining the risk type of the target road section based on the planned trajectory information of the target road section that the autonomous driving vehicle is to pass through, the predicted trajectory information of the obstacle vehicles on the target road section and at least one of the historical vehicle trajectory information of the target road section; and determining the control strategy for the autonomous driving vehicle based on the risk type of the target road section. The present disclosure can comprehensively and accurately detect the vehicle collision conflicts that may occur to the autonomous driving vehicle on the target road section, and can effectively reduce the risk of vehicle collision conflicts occurring to the autonomous driving vehicle on the target road section, thereby ensuring the safe driving of the autonomous driving vehicle.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular to a vehicle control method based on road section risk detection, a vehicle control device based on road section risk detection, an electronic device, a computer-readable storage medium, and a computer program product. Background Art

[0002] Autonomous vehicles operate in complex environments, with a wide variety of vehicles on the road and a high degree of randomness and uncertainty in driving behavior. These factors pose significant challenges to autonomous vehicle behavior planning. Currently, autonomous vehicle behavior planning primarily relies on predictions. For example, it detects the risk of collision with a predicted dynamic obstacle trajectory and plans dynamic response decisions. However, existing planning methods are limited in their ability to detect road risks and are unable to meet the needs of autonomous vehicle behavior planning in complex driving environments. Summary of the Invention

[0003] The embodiments of the present disclosure provide a vehicle control method and device based on road section risk detection, an electronic device, a medium and a product, which can solve or partially solve the above-mentioned deficiencies in the prior art or other deficiencies in the prior art.

[0004] According to the first aspect of the present disclosure, a vehicle control method based on road section risk detection is provided, including: determining the risk type of the target road section to be passed by the autonomous driving vehicle based on at least one of planned trajectory information of the target road section, predicted trajectory information of obstacle vehicles on the target road section, and historical vehicle trajectory information of the target road section; and determining a control strategy for the autonomous driving vehicle based on the risk type of the target road section.

[0005] According to the second aspect of the present disclosure, a vehicle control device based on road section risk detection is provided, including: a risk detection module, configured to determine the risk type of the target road section to be passed by the autonomous driving vehicle based on at least one of planned trajectory information of the target road section, predicted trajectory information of obstacle vehicles on the target road section, and historical vehicle trajectory information of the target road section; and a risk processing module, configured to determine a control strategy for the autonomous driving vehicle based on the risk type of the target road section.

[0006] The electronic device provided according to the third aspect of the present disclosure may include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the vehicle control method based on road section risk detection described in the first aspect of the present disclosure.

[0007] The computer-readable storage medium provided according to the fourth aspect of the present disclosure includes a computer program, which, when executed by a processor, implements the vehicle control method based on road section risk detection described in the first aspect of the present disclosure.

[0008] The computer program product provided according to the fifth aspect of the present disclosure stores a computer program, and when the computer program is executed by a processor, it implements the vehicle control method based on road section risk detection described in the first aspect of the present disclosure.

[0009] According to the vehicle control method and apparatus, electronic equipment, medium, and product based on road section risk detection provided by the embodiments of the present disclosure, the risk type of the target road section is determined based on at least one of the following information: the planned trajectory information of the target road section that the autonomous vehicle is to pass through, the predicted trajectory information of obstacle vehicles on the target road section, and the historical vehicle trajectory information of the target road section. By combining multiple pieces of information to perform risk detection on the target road section, it is possible to comprehensively and accurately detect vehicle collision conflicts that may occur with the autonomous vehicle on the target road section. Determining the control strategy for the autonomous vehicle based on the risk type of the target road section and controlling the autonomous vehicle can effectively reduce the risk of vehicle collision conflicts involving the autonomous vehicle on the target road section and ensure the safe driving of the autonomous vehicle.

[0010] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Other features, objects, and advantages of the present disclosure will become more apparent upon reading the detailed description of the non-limiting embodiments made with reference to the following drawings. The drawings are provided for a better understanding of the present invention and do not constitute a limitation of the present disclosure. Among them:

[0012] Figure 1 is a flow chart of a vehicle control method based on road section risk detection according to an embodiment of the present disclosure;

[0013] Figure 2 is a flow chart for determining a risk type of a target road segment according to some embodiments of the present disclosure;

[0014] Figure 3 is a flow chart for determining the risk type of a target road segment according to other embodiments of the present disclosure;

[0015] Figure 4 is a flowchart for determining the risk type of a target road segment according to yet other embodiments of the present disclosure;

[0016] Figure 5is a schematic diagram of aligning historical vehicle trajectory information according to some embodiments of the present disclosure;

[0017] Figure 6 is a schematic diagram of an application scenario of a vehicle control method based on road section risk detection according to an embodiment of the present disclosure;

[0018] Figure 7 is a block diagram of a vehicle control device based on road section risk detection according to an embodiment of the present disclosure;

[0019] Figure 8 is a block diagram of an example electronic device that can be used to implement embodiments of the present disclosure. DETAILED DESCRIPTION

[0020] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0021] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0022] An exemplary system architecture for implementing the speed planning method provided by the present disclosure may include a terminal device, a network, and a server. The network is used to provide a communication link between the terminal device and the server, and may include various connection types, such as a wired communication link, a wireless communication link, or an optical fiber cable.

[0023] Users can use terminal devices to interact with servers through the network to receive or send information, etc. Various client applications can be installed on the terminal devices, such as map, navigation, entertainment and other client applications.

[0024] The terminal device may be, for example, a vehicle-mounted system of a self-driving car, a delivery robot, or the like. The system may be implemented through hardware, software, or a combination of hardware and software.

[0025] The server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules (for example, to provide distributed services), or it can be implemented as a single software or software module. No specific limitations are given here.

[0026] It should be pointed out that the execution entity of the speed planning method provided by the present disclosure (hereinafter referred to as the "execution entity") can be the server in the above system architecture, the terminal device in the above system architecture, or the server and terminal device in the above system architecture.

[0027] When the speed planning method is executed by a server, the server can determine the risk type of the target section based on at least one of the planned trajectory information of the target section that the autonomous driving vehicle is to pass through, the predicted trajectory information of the obstacle vehicle on the target section, and the historical vehicle trajectory information of the target section, and then determine the control strategy for the autonomous driving vehicle based on the risk type of the target section, and send the control command to the terminal device, such as the vehicle-mounted system of the autonomous driving vehicle, and control the autonomous driving vehicle according to the control command through the vehicle-mounted system.

[0028] Another applicable scenario is that speed planning is completed directly by a terminal device, such as the vehicle-mounted system of an autonomous vehicle, instead of through a server. At this time, the vehicle-mounted system can determine the risk type of the target section based on the planned trajectory information of the target section that the autonomous vehicle is to pass through, the predicted trajectory information of the obstacle vehicle on the target section, and at least one of the historical vehicle trajectory information of the target section, and then determine the control strategy for the autonomous vehicle based on the risk type of the target section and control the autonomous vehicle.

[0029] In addition, speed planning can also be completed jointly by a server and a terminal device, such as the vehicle-mounted system of an autonomous vehicle. The present disclosure does not limit the operations performed by the server and the terminal device at this time. For example, the server can determine the risk type of the target section based on the planned trajectory information of the target section that the autonomous vehicle is to pass through, the predicted trajectory information of the obstacle vehicle on the target section, and at least one of the historical vehicle trajectory information of the target section, and then send the risk type of the target section to the vehicle-mounted system. The vehicle-mounted system can determine the control strategy for the autonomous vehicle based on the risk type of the target section and control the autonomous vehicle.

[0030] In addition, in the technical solutions involved in this disclosure, the acquisition, storage, use, processing, transportation, provision and disclosure of vehicle speed, trajectory information, etc. are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0031] An embodiment of the present disclosure provides a vehicle control method 100 based on road section risk detection.

[0032] Figure 1 FIG. 1 shows a flow chart of a vehicle control method 100 based on road section risk detection according to an embodiment of the present disclosure. Figure 1As shown, the vehicle control method 100 based on road section risk detection may include the following steps:

[0033] S101. Determine a risk type of a target road section based on at least one of planned trajectory information of the target road section that the autonomous driving vehicle is to pass through, predicted trajectory information of obstacle vehicles on the target road section, and historical vehicle trajectory information of the target road section.

[0034] S102. Determine a control strategy for the autonomous driving vehicle based on the risk type of the target road section.

[0035] In an embodiment of the present disclosure, the execution entity can determine the risk type of the target road section based on at least one of the planned trajectory information of the target road section that the autonomous driving vehicle is to pass through, the predicted trajectory information of the obstacle vehicle on the target road section, and the historical vehicle trajectory information of the target road section.

[0036] In an embodiment of the present disclosure, the executing entity may first obtain trajectory information of the autonomous vehicle. This trajectory information may refer to the planned trajectory information obtained by planning the trajectory of the autonomous vehicle for the target road section to be traversed. The planned trajectory information may include information such as the vehicle's position and speed. For example, the executing entity may obtain the planned trajectory information of the autonomous vehicle from the autonomous vehicle's planning module. The executing entity may also obtain trajectory information of an obstructing vehicle. This obstructing vehicle may refer to a vehicle traveling on the target road section to be traversed by the autonomous vehicle. This trajectory information may refer to predicted trajectory information obtained by predicting the obstructing vehicle's trajectory. This predicted trajectory information may include information such as the vehicle's position and speed. For example, the executing entity may obtain the predicted trajectory information of the obstructing vehicle from the autonomous vehicle's prediction module. The executing entity may also obtain historical vehicle trajectory information for the target road section. This historical vehicle trajectory information may refer to historical vehicle trajectory information of vehicles that have already passed through the target road section. This historical vehicle trajectory information may include information such as the vehicle's location. For example, the executing entity may obtain historical vehicle trajectory information for the target road section from an electronic map server using the autonomous vehicle's map application.

[0037] Then, the execution entity may perform a risk check on the target road segment based on at least one of the planned trajectory information, the predicted trajectory information, and the historical vehicle trajectory information, to determine whether the target road segment presents a risk of a vehicle collision conflict. If the target road segment presents a risk of a vehicle collision conflict, the execution entity may determine the risk type of the target road segment. Different road risk types may be predefined based on information about potential vehicle collision conflicts on the road, and the embodiments of the present disclosure do not limit the principles for setting road risk types. In one optional example, the execution entity may determine whether the target road segment presents a type of vehicle collision conflict. If the target road segment presents a type of vehicle collision conflict, the execution entity may determine the risk type of the target road segment. For example, the types of vehicle collision conflicts that may occur on the road segment may include explicit conflicts, potential conflicts, etc., and the embodiments of the present disclosure do not limit this. In another optional example, the execution entity may determine whether the target road segment presents a cause of a vehicle collision conflict. If the target road segment presents a cause of a vehicle collision conflict, the execution entity may determine the risk type of the target road segment. For example, the causes of vehicle collision conflicts that may occur on the road may include abnormal vehicle driving behavior, non-abnormal vehicle driving behavior, etc., and the embodiments of the present disclosure are not limited to this.

[0038] The executing entity can then determine a control strategy for the autonomous vehicle based on the risk type of the target road section and control the autonomous vehicle. Different vehicle control strategies can be predefined based on information about potential vehicle collisions on the road. The disclosed embodiments do not limit the principles for setting vehicle control strategies.

[0039] The vehicle control method based on road segment risk detection provided by the embodiments of the present disclosure determines the risk type of the target road segment based on at least one of the following information: the planned trajectory information of the target road segment that the autonomous vehicle is to traverse, the predicted trajectory information of obstacle vehicles on the target road segment, and the historical vehicle trajectory information of vehicles passing through the target road segment. By combining multiple pieces of information to perform risk detection on the target road segment, it is possible to comprehensively and accurately detect potential vehicle collision conflicts that the autonomous vehicle may encounter on the target road segment. Determining a control strategy for the autonomous vehicle based on the risk type of the target road segment and controlling the autonomous vehicle effectively reduces the risk of vehicle collision conflicts on the target road segment and ensures the safe operation of the autonomous vehicle.

[0040] It should be understood that the steps shown in method 100 are not exclusive, and other steps may be performed before, after, or between any of the steps shown. In addition, some of the steps shown may be performed simultaneously, or may be performed in a different order than the steps shown. Figure 1 Executed in the order shown.

[0041] Figure 2 FIG. 1 shows a flow chart for determining the risk type of a target road segment according to some embodiments of the present disclosure. Figure 2 As shown, step S101 determines the risk type of the target road section based on at least one of the planned trajectory information of the target road section that the autonomous driving vehicle is to pass, the predicted trajectory information of the obstacle vehicle on the target road section, and the historical vehicle trajectory information of the target road section, and may include the following steps:

[0042] S201: Determine whether there is a vehicle conflict area on the target road section based on the planned trajectory information and the predicted trajectory information.

[0043] In response to the presence of a vehicle conflict area in the target road section, operation S202 is performed. Otherwise, the process ends.

[0044] S202: Based on the planned trajectory information, determine whether the autonomous driving vehicle has a specific driving behavior.

[0045] In response to the autonomous driving vehicle not having a specific driving behavior, operation S203 is performed. In response to the autonomous driving vehicle having a specific driving behavior, operation S204 is performed.

[0046] S203: Determine that the risk type of the target road section is the first type of risk.

[0047] S204: Determine that the risk type of the target road section is the second type of risk.

[0048] In the embodiments of the present disclosure, situations where an autonomous vehicle might collide with another vehicle, excluding specific driving behaviors, can be defined as the first type of risk. A second type of risk can be defined as situations where an autonomous vehicle might collide with another vehicle using specific driving behaviors. Specific driving behaviors can be set as needed and are not limited in the embodiments of the present disclosure. For example, specific driving behaviors may include turning, merging, and diverging.

[0049] In an embodiment of the present disclosure, the executing entity can determine whether there is a collision conflict area between the autonomous driving vehicle and the obstacle vehicle in the target road section based on the planned trajectory information and the predicted trajectory information. When it is determined that there is no collision conflict area between the autonomous driving vehicle and the obstacle vehicle in the target road section, the process of the vehicle control method based on road section risk detection can be terminated. When it is determined that there is a collision conflict area between the autonomous driving vehicle and the obstacle vehicle in the target road section, it can be determined that there is a clear conflict in the target road section. It can be further determined whether there is a specific driving behavior of the autonomous driving vehicle based on the planned trajectory information. When it is determined that the autonomous driving vehicle does not have the specific driving behavior, the risk type of the target road section can be determined to be a first type of risk. When it is determined that the autonomous driving vehicle has a specific driving behavior, the risk type of the target road section can be determined to be a second type of risk.

[0050] This embodiment can determine the cause of the collision conflict by detecting the specific driving behavior of the autonomous driving vehicle, and can focus on the risky behavior of the autonomous driving vehicle, which is conducive to controlling the autonomous driving vehicle and reducing the risk of vehicle collision conflict involving the autonomous driving vehicle.

[0051] In some optional embodiments of the present disclosure, the situation where the distance between two vehicles at the same time approaches a certain distance or less can be defined as a vehicle collision conflict. A safety distance can be pre-set, and when the distance between two vehicles at the same time is less than the pre-set safety distance, it can be considered that the two vehicles have a collision conflict. The vehicle conflict area may refer to an area where the distance between the trajectories of two vehicles at the same time is less than the safety distance. Optionally, step S201 determines whether there is a vehicle conflict area in the target road section based on the planned trajectory information and the predicted trajectory information, and may include the following steps: determining the distance between the planned trajectory and the predicted trajectory at the same time based on the coordinates of each trajectory point in the planned trajectory information and the coordinates of each trajectory point in the predicted trajectory information; determining whether the distance between the planned trajectory and the predicted trajectory at the same time is less than the preset safety distance; and determining that there is a vehicle conflict area in the target road section in response to the distance between the planned trajectory and the predicted trajectory at the same time being less than the preset safety distance.

[0052] In an optional example, the process of determining whether there is a vehicle conflict area on the target road section is as follows:

[0053] a. Trajectory equations of the two vehicles:

[0054] The trajectory equation of car 1 is: ;

[0055] The trajectory equation of car 2 is: .

[0056] Among them, vehicle 1 can be an autonomous driving vehicle, and vehicle 2 can be an obstacle vehicle.

[0057] b. Distance between vehicle trajectories: The Euclidean distance between two vehicle trajectories: .

[0058] in, ( t ) is the horizontal coordinate of the trajectory point of vehicle 1, is the ordinate of the trajectory point of vehicle 1, is the horizontal coordinate of the trajectory point of vehicle 2, is the ordinate of the trajectory point of vehicle 2.

[0059] c. Vehicle conflict area:

[0060] The vehicle conflict area can be determined by the following formula 1:

[0061] (Formula 1)

[0062] Among them, the conditions for collision conflict are , is the empty set, It's a safe distance.

[0063] In some optional embodiments of the present disclosure, a specific driving behavior of an autonomous vehicle can be narrowly defined as a driving state in which the planned trajectory of the autonomous vehicle fluctuates, making the autonomous vehicle susceptible to collisions with other vehicles. For example, trajectory fluctuations may be caused by driving states such as merging, diverging, changing lanes, detouring, and turning at intersections. Whether the autonomous vehicle exhibits a specific driving behavior can be determined by performing change point detection on the planned trajectory information in a world coordinate system. Optionally, step S202, determining whether the autonomous vehicle exhibits a specific driving behavior based on the planned trajectory information, may include the following steps: determining the curvature of each trajectory point based on the time information and position information of each trajectory point in the predicted trajectory information; determining a standard score for each trajectory point based on the position information and curvature of each trajectory point; determining whether the standard score of each trajectory point is greater than a preset first threshold; and determining that the autonomous vehicle exhibits a specific driving behavior in response to a trajectory point having a standard score greater than the preset first threshold among the trajectory points.

[0064] This embodiment uses a change point detection method in a world coordinate system to accurately identify specific driving behaviors of autonomous vehicles, providing support for controlling autonomous vehicles and reducing the risk of vehicle collision conflicts.

[0065] In an optional example, a standard score, also known as a Z-score, smoothing algorithm can be used to analyze the planned trajectory of the autonomous vehicle to determine whether the autonomous vehicle exhibits specific driving behavior. The process is as follows:

[0066] a. Data preparation:

[0067] Get the vehicle's trajectory data, including the timestamp of the trajectory point, the horizontal coordinate x and the vertical coordinate y in the world coordinate system;

[0068] b. Calculate curvature:

[0069] Curvature is an important indicator used to describe the degree of curvature of a trajectory. For the trajectory equation of a two-dimensional curve, its curvature κ can be calculated using the following formula 2:

[0070] (Formula 2)

[0071] in, is the first derivative of x with respect to time, is the time derivative of y, is the second derivative of x with respect to time, is the second derivative of y with respect to time.

[0072] The first and second derivatives can be calculated using the central difference method. The specific formula is as follows:

[0073] (Formula 3) (Formula 4)

[0074] (Formula 5) (Formula 6)

[0075] Where i is the trajectory point where the derivative is calculated, and Δt is the time interval between two adjacent trajectory points.

[0076] c. Calculate the standard score:

[0077] In order to identify outliers, the Z-score of each trajectory point can be calculated. The Z-score can represent the degree of deviation of each trajectory point from the mean, and its calculation formula is as follows:

[0078] (Formula 7)

[0079] Where X={ x , y , κ} are the coordinates and curvature of the trajectory points , μ is the mean of all points in the trajectory, σ is the standard deviation of each trajectory point in the trajectory, and the Z-score is calculated for the x, y and κ values of each trajectory point.

[0080] d. Abnormal point judgment:

[0081] The x, y, and κ thresholds of the trajectory points can be pre-set to determine whether there are abnormal trajectory points. The calculation formula is as follows:

[0082] (Formula 8)

[0083] in It is the Z-score threshold. You can choose the appropriate Z-score threshold according to the specific application scenario and then conduct risk assessment for the corresponding scenario.

[0084] Figure 3 FIG. 4 shows a flow chart of determining the risk type of a target road segment according to other embodiments of the present disclosure. Figure 3 As shown, step S101 determines the risk type of the target road section based on at least one of the planned trajectory information of the target road section that the autonomous driving vehicle is to pass, the predicted trajectory information of the obstacle vehicle on the target road section, and the historical vehicle trajectory information of the target road section, and may include the following steps:

[0085] S301: Based on the predicted trajectory information and historical vehicle trajectory information, determine whether the obstructing vehicle has abnormal driving behavior.

[0086] In response to the obstacle vehicle having abnormal driving behavior, operation S302 is executed; in response to the obstacle vehicle not having abnormal driving behavior, operation 303 is executed.

[0087] S302: Determine that the risk type of the target road section is the third risk type.

[0088] S303: Based on the planned trajectory information and the predicted trajectory information, determine whether there is a vehicle conflict area on the target road section.

[0089] In response to the presence of a vehicle conflict area in the target road section, operation S304 is performed. Otherwise, the process ends.

[0090] S304: Based on the planned trajectory information, determine whether the autonomous driving vehicle has a specific driving behavior.

[0091] In response to the autonomous driving vehicle not having a specific driving behavior, operation S305 is performed. In response to the autonomous driving vehicle having a specific driving behavior, operation S306 is performed.

[0092] S305: Determine that the risk type of the target road section is the first type of risk.

[0093] S306: Determine that the risk type of the target road section is the second type of risk.

[0094] In the embodiments of the present disclosure, the first category of risk is defined as situations where an autonomous vehicle could collide with another vehicle, except for specific driving behaviors. The second category of risk is defined as situations where an autonomous vehicle could collide with another vehicle using specific driving behaviors. The third category of risk is defined as situations where another vehicle's abnormal driving behavior could potentially collide with the autonomous vehicle. For example, another vehicle overtaking in the opposite lane could result in a collision with the autonomous vehicle.

[0095] In the embodiment of the present disclosure, the execution subject can judge whether the obstructing vehicle has passed the target section according to the historical vehicle trajectory of the target section based on the predicted trajectory information and the historical vehicle trajectory information. When it is determined that the obstructing vehicle has not passed the target section according to the historical vehicle trajectory of the target section, it can be determined that the obstructing vehicle has abnormal driving behavior and there is a potential conflict in the target section. It can be further determined that the risk type of the target section is the third type of risk. When it is determined that the obstructing vehicle has passed the target section according to the historical vehicle trajectory of the target section, it can be determined that the obstructing vehicle has no abnormal driving behavior. It can be further determined whether there is a collision conflict area between the autonomous driving vehicle and the obstructing vehicle in the target section based on the planned trajectory information and the predicted trajectory information. Among them, the description of analyzing whether there is a vehicle collision conflict area in the target section based on the planned trajectory information and the predicted trajectory information can be found in Figure 2 The relevant contents will not be elaborated here.

[0096] This embodiment can identify the potential risks in the target road section by detecting the abnormal driving behavior of the obstacle vehicle, so that the autonomous driving vehicle can be effectively controlled according to the cause of the risk, which is conducive to reducing the risk of vehicle collision conflicts involving the autonomous driving vehicle and ensuring the safe driving of the autonomous driving vehicle.

[0097] In some optional embodiments of the present disclosure, a dataset of historical vehicle trajectories on a target road section can be clustered to obtain clusters of vehicle trajectories, thereby forming a vehicle corridor. Abnormal driving behavior of an obstructing vehicle can be defined as the predicted trajectory of the obstructing vehicle not following any of the trajectory clusters of vehicles passing through the road section. Kernel density estimation (KDE) can be used to assess whether the predicted trajectory information belongs to known trajectory clusters to determine whether the obstructing vehicle has abnormal driving behavior. Optionally, step S301 determines whether the obstructing vehicle has abnormal driving behavior based on the predicted trajectory information and the historical vehicle trajectory information, and may include the following steps: clustering the historical vehicle trajectory information to obtain trajectory clusters of the historical vehicle trajectory information; performing kernel density estimation on each trajectory cluster to obtain a probability density function of each trajectory cluster; determining a probability density value of the predicted trajectory information belonging to each trajectory cluster based on the probability density function of each trajectory cluster and the coordinates of each trajectory point in the predicted trajectory information; determining whether the probability density value of the predicted trajectory information belonging to each trajectory cluster is greater than a preset second threshold; and in response to the probability density values of the predicted trajectory information belonging to each trajectory cluster being less than or equal to the preset second threshold, determining that the obstructing vehicle has abnormal driving behavior.

[0098] In an optional example, the trajectory cluster set obtained by clustering is ( ), where each cluster Contains multiple tracks, and each track can be a series of point tracks The process of judging whether the obstacle vehicle has abnormal driving behavior is as follows:

[0099] a. Data preparation:

[0100] Get a set of track points for a track A type of trajectory cluster in the trajectory cluster obtained by clustering ;

[0101] b. Kernel density estimation:

[0102] Trajectory Cluster The trajectory points of all trajectories in are merged into one set , which is calculated as follows:

[0103] (Formula 9)

[0104] in, is a cluster of trajectories The j Then, for each trajectory cluster Collection Perform kernel density estimation to obtain the corresponding probability density function, which is calculated as follows:

[0105] (Formula 10)

[0106] in, Trajectory cluster The number of trajectory points, h is the bandwidth parameter, K ( u,v ) is the kernel function, and a two-dimensional Gaussian kernel function can be selected. Its calculation formula is as follows:

[0107] (Formula 11)

[0108] in, , .

[0109] c. Evaluation trajectory:

[0110] For each trajectory point of trajectory A , calculate its trajectory cluster The probability density value of is calculated as follows:

[0111] (Formula 12)

[0112] in, m It's a trajectory A The number of trajectory points in .

[0113] d. Trajectory identification:

[0114] It is conceivable to set a threshold τ if ( A ) is greater than the threshold, the trajectory is considered A Belongs to the trajectory cluster , which is calculated as follows:

[0115] if (Formula 13)

[0116] e. Abnormal determination:

[0117] Traverse all clustered trajectory clusters and repeat steps a to d to determine the trajectory A Whether it belongs to each type of trajectory cluster.

[0118] If the trajectory A If a trajectory does not belong to any type of trajectory cluster, then the trajectory is considered A Abnormal driving behavior.

[0119] In some optional embodiments of the present disclosure, clustering historical vehicle trajectory information to obtain trajectory clusters of the historical vehicle trajectory information may include the following steps: aligning, segmenting, and sampling the historical vehicle trajectory information based on the planned trajectory information; and clustering the historical vehicle trajectory information based on the coordinates of the sampling points of each segmented trajectory segment to obtain trajectory clusters of the historical vehicle trajectory information. Optionally, clustering the historical vehicle trajectory information may employ K-means clustering. Optionally, clustering the historical vehicle trajectory information based on the coordinates of the sampling points of each segmented trajectory segment to obtain trajectory clusters of the historical vehicle trajectory information may include: traversing each number of clusters in a preset set, performing K-means clustering corresponding to the number of clusters based on the coordinates of the sampling points of each segmented trajectory segment, and determining the DB index of each clustered trajectory cluster; and comparing the DB indexes of the K-means clusters of each number of clusters, and selecting the trajectory clusters obtained by the K-means clustering of the cluster number with the smallest DB index as the trajectory clusters of the historical vehicle trajectory information.

[0120] In an optional example, in order to facilitate the comparison of historical vehicle trajectory information, the historical vehicle trajectory information can be aligned with a suitable position based on the environmental road information, with the normal direction of the road longitudinal section as the positive direction. The environmental road information can be obtained from the electronic map server. The starting point of the shortest trajectory in the historical vehicle trajectory information in the same direction can be selected for alignment. Figure 5 As shown, taking the intersection as an example, between trajectory 501 and trajectory 502, trajectory 502 is relatively shorter, and the starting point of trajectory 502 is selected to align trajectory 501 and trajectory 502; between trajectory 502 and trajectory 503, trajectory 503 is relatively shorter, and the starting point of trajectory 503 is selected to align trajectory 502 and trajectory 503; between trajectory 504 and trajectory 505, trajectory 504 is relatively shorter, and the starting point of trajectory 504 is selected to align trajectory 504 and trajectory 505.

[0121] After the historical vehicle trajectory information is aligned, the historical vehicle trajectory information can be divided into N segments starting from the position where the historical vehicle trajectory information is aligned, according to the reference line direction of the planned trajectory information, and each trajectory segment obtained by the division is sampled separately, and the position coordinates of the sampling points are used as the characteristics of the trajectory. The similarity between the two trajectories can be measured by calculating the distance between each trajectory segment. Among them, the number and length of the trajectory segments into which the historical vehicle trajectory information is divided can be set as needed, and the embodiments of the present disclosure do not limit this. The number of sampling points for sampling each trajectory segment can be set as needed, and the embodiments of the present disclosure do not limit this. For example, all historical trajectories of the target section can be divided into trajectory segments of the same number and length, and the same number of sampling points can be sampled for the trajectory segments obtained by dividing all historical trajectories of the target section.

[0122] In an optional example, the process of implementing K-means clustering on the historical trajectories of the target road segment is as follows:

[0123] a. Select the number of clusters K;

[0124] b. Select initial cluster centers: randomly select K trajectories from the dataset as initial cluster centers;

[0125] c. Assign data points: For each trajectory, calculate its distance from all cluster centers and assign it to the cluster center closest to it. Repeat this process until all trajectories are assigned to the corresponding cluster centers.

[0126] d. Update cluster centers: After all trajectories are assigned to corresponding cluster centers, update the cluster center of each class. The new cluster center is the average value of all trajectories in the class. For example, a class containing trajectories A and B , the new cluster center is the average trajectory of trajectories A and B;

[0127] e. Iteration: Repeat steps c and d until the cluster center no longer changes or changes very little, indicating that the clusters obtained by clustering have converged, and calculate their DB index;

[0128] f. Sampling: Traverse the number of clusters in the cluster number set, execute steps a to e, and select the cluster number k with the smallest DB index as the final clustering result of the trajectory.

[0129] Optionally, to determine the distance metric for similarity, the Euclidean distance between multiple trajectories can be used to calculate the similarity, and the calculation formula is as follows:

[0130] (Formula 14)

[0131] in, and is the coordinate of the specific sampling point between the two trajectories, N is the number of sampling points. The distance between two types of trajectory clusters can be measured by the centroid distance between the two types of trajectory clusters.

[0132] Optionally, the process of calculating the DB index for the clustered trajectory clusters is as follows:

[0133] a. Calculate the spread of each trajectory cluster: For the trajectory cluster , calculate the dispersion of its internal trajectory ;

[0134] b. Calculate the distance between trajectory clusters: For any two types of trajectory clusters and , calculate the distance between them , that is, the distance between the centroids of the two types of trajectory clusters;

[0135] c. Calculate similarity measure: for trajectory clusters and , calculate their similarity , which is calculated as follows:

[0136] (Formula 15)

[0137] d. Select the best similarity metric: for trajectory clusters , find the most similar trajectory cluster , and record the similarity measure between the two as the DB index, which is calculated as follows:

[0138] (Formula 16)

[0139] e. Calculate the final DB index: Calculate the average value of the DB index of all trajectory clusters as the final DB index. The calculation formula is as follows:

[0140] (Formula 17)

[0141] Among them, the DB index is used to determine the local optimal cluster number. For a given trajectory dataset X, it can be divided into k categories , for the trajectory cluster , is a cluster of trajectories The number of samples in is a cluster of trajectories The center of mass, is a cluster of trajectories and The distance measure between ， is a cluster of trajectories The average spread of , Trajectory cluster Any trajectory in Trajectory cluster The number of trajectories in .

[0142] Figure 4 FIG. 4 shows a flow chart of determining the risk type of a target road segment according to some further embodiments of the present disclosure. Figure 4As shown, step S101 determines the risk type of the target road section based on at least one of the planned trajectory information of the target road section that the autonomous driving vehicle is to pass, the predicted trajectory information of the obstacle vehicle on the target road section, and the historical vehicle trajectory information of the target road section, and may include the following steps:

[0143] S401: Based on the planned trajectory information and the predicted trajectory information, determine whether there is a vehicle conflict area on the target road section.

[0144] In response to the presence of a vehicle conflict area on the target road section, operation S402 is performed; in response to the absence of a vehicle conflict area on the target road section, operation S403 is performed.

[0145] S402: Based on the planned trajectory information, determine whether the autonomous driving vehicle has a specific driving behavior.

[0146] In response to the autonomous driving vehicle not having a specific driving behavior, operation S404 is performed. In response to the autonomous driving vehicle having a specific driving behavior, operation S405 is performed.

[0147] S404: Determine that the risk type of the target road section is the first type of risk.

[0148] S405: Determine that the risk type of the target road section is the second type of risk.

[0149] S403: Based on historical vehicle trajectory information, determine whether there is a conflict-prone area on the target road section.

[0150] In response to the target road section having a high-conflict area, S406 is executed. Otherwise, the process ends.

[0151] S406. Determine that the risk type of the target road section is the fourth risk type.

[0152] In the embodiments of the present disclosure, situations where an autonomous vehicle might collide with another vehicle, except for specific driving behaviors, can be defined as the first type of risk. Situations where an autonomous vehicle might collide with another vehicle using specific driving behaviors can be defined as the second type of risk. Situations where a road section marked as a collision-prone section based on empirical road data, but where no collision potential is detected based on current data, can be defined as the fourth type of risk.

[0153] In an embodiment of the present disclosure, the execution entity can determine whether there is a collision conflict area between the autonomous driving vehicle and the obstacle vehicle in the target road section based on the planned trajectory information and the predicted trajectory information. When it is determined that there is a collision conflict area between the autonomous driving vehicle and the obstacle vehicle in the target road section, it can be determined that there is a clear conflict in the target road section. The execution entity can further analyze whether there is a specific driving behavior of the autonomous driving vehicle based on the planned trajectory information. When it is determined that the autonomous driving vehicle does not have a specific driving behavior, it can be determined that the risk type of the target road section is a first type of risk. When it is determined that the autonomous driving vehicle has a specific driving behavior, it can be determined that the risk type of the target road section is a second type of risk. When it is determined that there is no collision conflict area between the autonomous driving vehicle and the obstacle vehicle in the target road section, it can further analyze whether there is a conflict-prone area in the target road section based on historical vehicle trajectory information. When it is determined that there is no conflict-prone area in the target road section, the process of the vehicle control method based on road section risk detection can be terminated. When it is determined that there is a conflict-prone area in the target road section, it can be determined that there is a potential conflict in the target road section, and the risk type of the target road section can be determined as a fourth type of risk.

[0154] This embodiment determines conflict-prone areas through historical vehicle trajectory information, and can identify potential risks in target road sections, so that the autonomous driving vehicle can be effectively controlled according to the cause of the risk, which is conducive to reducing the risk of vehicle collision conflicts involving autonomous driving vehicles and ensuring the safe driving of autonomous driving vehicles.

[0155] In some optional embodiments of the present disclosure, for Class I or Class II risks, the autonomous vehicle's driving trajectory can be adjusted according to a fuzzy control strategy, and a general risk warning message "Beware of Risk" can be generated to indicate the risk. Optionally, step 102 determines the control strategy for the autonomous vehicle based on the risk type of the target road segment, and may include the following steps: in response to the target road segment's risk type being Class I or Class II risk, determining the membership of the autonomous vehicle's output state as acceleration, deceleration, and constant speed based on preset fuzzy rules, the distance between the autonomous vehicle and the obstacle vehicle, and the speed difference; determining the center of gravity value of the membership, and adjusting the autonomous vehicle's driving speed based on the center of gravity value.

[0156] This embodiment adopts a fuzzy control strategy to adjust the driving speed of the autonomous driving vehicle, which can effectively reduce the risk of vehicle collision conflicts in the target road section and ensure the safe driving of the autonomous driving vehicle.

[0157] Optionally, the preset fuzzy rules may include:

[0158] If the distance is close and the speed difference is large, the output is to moderately accelerate or maintain the speed;

[0159] If the distance is close and the speed difference is moderate, the output is to maintain the speed or moderately slow down;

[0160] If the distance is moderate and the speed difference is moderate, the output is to maintain the speed;

[0161] If the distance is far and the speed difference is moderate, the output is moderate acceleration or maintaining speed;

[0162] If the distance is close and the speed difference is small, the output is to maintain the speed or moderately decelerate;

[0163] If the distance is moderate and the speed difference is small, the output is moderate acceleration or maintaining speed;

[0164] If the distance is far and the speed difference is small, the output is moderate acceleration or maintaining speed.

[0165] In an alternative example, since the first and second types of risks are characterized by clear conflict processes, active safety handling can be performed. The fuzzy control strategy can be used to adjust the speed of the autonomous vehicle to avoid collisions. The implementation process is as follows:

[0166] a. Input variables: distance and speed difference between vehicles;

[0167] b. Output variables: Acceleration: refers to the degree of vehicle acceleration;

[0168] Deceleration: refers to the degree to which a vehicle slows down;

[0169] Maintain Speed: Maintain the current speed under certain circumstances;

[0170] Among them, the control goal is to maintain a safe distance by adjusting the vehicle's driving trajectory, and the output variable should be directly related to the control goal.

[0171] c. Fuzzy membership function: for the distance between vehicles

[0172] Near: Indicates that the distance between the autonomous vehicle and the collision vehicle is small.

[0173] (Formula 18)

[0174] in, is the upper limit of the distance "close", is the distance between vehicles The degree of membership to the fuzzy set (Near) indicating that the distance between the autonomous vehicle and the collision vehicle is small.

[0175] Medium: Indicates that the distance between the autonomous vehicle and the collision vehicle is moderate.

[0176] (Formula 19)

[0177] in, is the center value of the "moderate" distance, is the distance between vehicles The degree of membership in the fuzzy set (Medium) representing the moderate distance between the autonomous vehicle and the collision vehicle.

[0178] Far: Indicates that the distance between the autonomous vehicle and the collision vehicle is large.

[0179] (Formula 20)

[0180] in, is the lower limit of distance "far", is the distance between vehicles The degree of membership to the fuzzy set (Far) representing the larger distance between the autonomous vehicle and the collision vehicle.

[0181] d. Fuzzy membership function: For speed difference, the speed difference is a relative value, which is the difference between the speed of the autonomous vehicle and the collision vehicle. Its value is V .

[0182] Small: Indicates that the speed difference between the autonomous vehicle and the collision vehicle is small.

[0183] (Formula 21)

[0184] in, is the upper limit of the speed difference "small", It's the speed difference The membership degree of the fuzzy set (small) indicating that the speed difference between the autonomous vehicle and the collision vehicle is small.

[0185] Moderate: Indicates that the speed difference between the autonomous vehicle and the collision vehicle is moderate.

[0186] (Formula 22)

[0187] in, is the center value of the "moderate" speed difference, It's the speed difference The degree of membership in the fuzzy set (moderate) indicating that the speed difference between the autonomous vehicle and the collision vehicle is moderate.

[0188] Big: Indicates that the speed difference between the autonomous vehicle and the collision vehicle is large.

[0189] (Formula 23)

[0190] in, is the upper limit of how “large” the speed difference can be, It's the speed difference The degree of membership to the fuzzy set (big) representing the large speed difference between the autonomous vehicle and the collision vehicle.

[0191] e. Fuzzy rules: Write corresponding fuzzy rules based on the membership functions of output variables and input variables.

[0192] Rule 1: If the distance is “close” and the speed difference is “large”, then output “moderate acceleration or maintain speed” (AK).

[0193] Rule 2: If the distance is “close” and the speed difference is “moderate”, then output “maintain speed or moderately slow down” (KD).

[0194] Rule 3: If the distance is "moderate" and the speed difference is "moderate", then output "maintain speed" (K).

[0195] Rule 4: If the distance is "far" and the speed difference is "moderate", then output "moderate acceleration or maintain speed" (AK).

[0196] Rule 5: If the distance is “close” and the speed difference is “small”, then output “maintain speed or decelerate” (KD).

[0197] Rule 6: If the distance is "moderate" and the speed difference is "small", then output "moderate acceleration or maintain speed" (AK).

[0198] Rule 7: If the distance is "far" and the speed difference is "small", then output "moderate acceleration or maintain speed" (AK).

[0199] f. Fuzzy set: Normalize the fuzzy membership values of speed difference and distance.

[0200] The distance normalization results are as follows:

[0201] (Formula 24)

[0202] (Formula 25)

[0203] (Formula 26)

[0204] The normalized results of the speed difference are as follows:

[0205] (Formula 27)

[0206] (Formula 28)

[0207] (Formula 29)

[0208] Define a corresponding fuzzy set for each output variable. The fuzzy set can use membership functions to represent the different states of these output variables. We assume that the above fuzzy rules and their corresponding outputs are uniform, then the fuzzy membership is calculated as follows.

[0209] Acceleration: Indicates the state where the autonomous vehicle needs to accelerate moderately. μA (1) is:

[0210]

[0211] (Formula 30)

[0212] Deceleration: Indicates that the autonomous vehicle needs to moderately decelerate. μD( -1) is:

[0213] (Formula 31)

[0214] Maintain Speed: Indicates that the autonomous vehicle needs to continue driving at the current speed. μK (0) is:

[0215]

[0216]

[0217] (Formula 32)

[0218] g. Defuzzification: Defuzzification is performed using the Center of Gravity (CoG) method to calculate the center of gravity of the fuzzy output. Assuming the membership function range is [-1, 0, 1], the corresponding membership values are as follows:

[0219] Accelerate: (1)= ;

[0220] Decelerate (-1)= ;

[0221] Maintain Speed: (0)= ;

[0222] Center of gravity It can be calculated by the following formula:

[0223] (Formula 33)

[0224] The above formula can be simplified into a weighted average form:

[0225] (Formula 34)

[0226] According to the calculation results The approximate relationship with [-1,0,1] determines the driving strategy that the autonomous vehicle should choose. For example, ≈1, the autonomous vehicle should choose to accelerate.

[0227] h. Output control signal:

[0228] Design the output variables of the fuzzy controller: ,in, Is the output control signal. Set the desired speed of the acceleration, deceleration, and uniform speed target as , the stopping speed is , the current speed is .in, The minimum creep speed is set, and the empirical value can be 0.1. The degree of acceleration or deceleration is determined by the fuzzy center of gravity value. Determine, which indirectly affects the time to reach the target speed and affects the effect of acceleration or deceleration.

[0229] For acceleration, it is assumed that the maximum acceleration of the autonomous vehicle is , then the autonomous vehicle is at the current speed v Accelerate to the desired speed The time required is , this time is the fastest acceleration time. In addition, set the slowest acceleration time to , then the speed-up time interval is , so we have the following formula:

[0230] (Formula 35)

[0231] Similarly, for deceleration, it is assumed that the maximum deceleration of the autonomous vehicle is , then the autonomous vehicle is at the current speed v Decelerate to a stop The time required is , which is the fastest braking time. In addition, set the slowest braking time to , then the deceleration time interval is [ , so we have the following formula:

[0232] (Formula 36)

[0233] For constant speed driving, to avoid the current speed =0 will cause the vehicle to stop, so the following formula is set:

[0234] (Formula 37)

[0235] in, is the output control signal.

[0236] In some optional embodiments of the present disclosure, for the third type of risk, the autonomous vehicle can be controlled to slow down and stop based on a strategy for stopping when the distance between the autonomous vehicle and the obstacle vehicle is less than or equal to a preset safety distance. A "pay special attention" risk warning message can also be generated to indicate the risk. Optionally, step 102 determines the control strategy for the autonomous vehicle based on the risk type of the target road segment, and may include: in response to the target road segment's risk type being the third type of risk, controlling the autonomous vehicle to slow down and stop based on the autonomous vehicle's current speed, the obstacle vehicle's current speed, a preset reduction factor, the current distance between the autonomous vehicle and the obstacle vehicle, and a preset safety distance.

[0237] This embodiment can minimize the risk of vehicle collision and conflict by controlling the autonomous driving vehicle to slow down and stop within a safe distance for observation, thereby ensuring the safe driving of the autonomous driving vehicle.

[0238] In an optional example, since the third type of risk is characterized by the uncertainty of the possible future collision process, passive safety processing can be performed. Such risk data, namely the vehicle's position and speed information, should be reported. Since the driving strategy of the obstructing vehicle deviates greatly from the driving data of past vehicles, such as the possibility of illegal driving behaviors such as driving against traffic, its future behavior cannot be rationally inferred. Therefore, the worst case scenario should be considered, that is, when the obstructing vehicle is at a safe distance from the autonomous vehicle. When the vehicle is within the range, the autonomous vehicle should stop and observe. The implementation process is as follows:

[0239] For this type of deterministic problem, the current speed of the autonomous vehicle is v , the speed of the abnormally moving obstacle vehicle is The distance between vehicles is d (> ), then according to the deceleration of the abnormally moving obstacle vehicle, the reduction coefficient λ of the driving distance from the autonomous driving vehicle to the abnormally moving obstacle vehicle is reasonably set, , the calculation formula of the output control signal is as follows:

[0240] (Formula 38)

[0241] For example, if an abnormally moving obstacle vehicle slows down, you can set =1; if the abnormally moving obstacle vehicle does not slow down, you can set <1.

[0242] In some optional embodiments of the present disclosure, for the fourth type of risk, the autonomous driving vehicle can be controlled to travel at a limited speed based on the two-point boundary value optimal control (Optimal Bundary Value Problem, abbreviated as OBVP) strategy, and a risk warning message of "pay attention" can be generated to indicate the risk. Optionally, step 102 determines the control strategy for the autonomous driving vehicle based on the risk type of the target road section, and can include the following steps: in response to the risk type of the target road section being the fourth type of risk, the current position of the autonomous driving vehicle is used as the first point, and a first state is determined based on the current speed and acceleration of the autonomous driving vehicle; the position closest to the first point in the conflict-prone area is used as the second point, and a second state is determined based on the distance between the conflict-prone area and the first point and the preset speed limit; based on the first state and the second state, a quintic spline curve state transition trajectory and state transition time from the first point to the second point are determined to control the autonomous driving vehicle to travel at a limited speed.

[0243] This embodiment adopts a two-point boundary value optimal control strategy to control the speed limit of autonomous driving vehicles to address the potential risks generated in areas with frequent conflicts. This can effectively reduce the risk of vehicle collision conflicts and ensure the safe driving of autonomous driving vehicles.

[0244] In an alternative example, due to the characteristics of the fourth risk category, it is known that there is a historically high-risk area on the road ahead, but no vehicles involved in collisions are currently observed. Therefore, preventive safety measures can be taken. The autonomous vehicle can be controlled to limit its speed according to the two-point boundary value optimal control strategy and observe to prevent danger. The implementation process is as follows:

[0245] Construct a general two-point boundary value optimal control problem and determine the starting state as the current state , assuming that the conflict-prone area is m meters, the speed limit is , then the target state is , the state transfer process selects the quintic spline curve, the state transfer time is the output control signal, and the calculation formula is as follows:

[0246] (Formula 39)

[0247] in, Fixed transfer time.

[0248] Figure 6 FIG1 shows a schematic diagram of an application scenario of a vehicle control method based on road section risk detection according to an embodiment of the present disclosure. Figure 6 As shown in the figure, the specific steps for autonomous driving vehicles to perform road section risk detection and control are as follows:

[0249] Step 1: Acquire historical traffic data 611 of the target road section, including historical vehicle trajectory information and environmental road information;

[0250] Step 2: Cluster the historical vehicle trajectory information based on the historical traffic data 611, and perform risk detection on the target road section based on the planned trajectory information 612 of the autonomous driving vehicle and the predicted trajectory information 613 of the obstacle vehicle, specifically including:

[0251] Step 621: Identify abnormal driving behavior of the obstructing vehicle based on the predicted trajectory information and historical vehicle trajectory information;

[0252] Step 622: Determine whether there is a vehicle conflict area on the target road section based on the planned trajectory information and the predicted trajectory information;

[0253] Step 623: Identify specific driving behaviors of the autonomous driving vehicle based on the planned trajectory information;

[0254] Step 624: Determine whether there is a high-conflict area on the target road section based on historical vehicle trajectory information;

[0255] Step 3: Conduct risk analysis and determine the safety control strategy for the autonomous vehicle based on the risk type, including:

[0256] Step 631: For abnormal driving behavior of the obstructing vehicle, prompt "pay special attention", slow down and stop to observe, monitor risks, and make emergency response preparations;

[0257] Step 632: If there is a vehicle conflict area on the target road section, a "Beware of Risk" prompt is displayed, and active response measures are taken: the driving trajectory of the autonomous driving vehicle is adjusted;

[0258] Step 633: For specific driving behaviors of the autonomous vehicle, a "Beware of Risk" prompt is issued, and proactive response measures are taken: adjusting the driving trajectory of the autonomous vehicle;

[0259] Step 634: For areas with high conflict rates on the target road section, a prompt "Pay attention and observe" is given, and preventive speed limit processing is performed: the autonomous driving vehicle is controlled to travel at a limited speed.

[0260] The embodiment of the present disclosure also provides a vehicle control device based on road section risk detection, Figure 7 FIG2 shows a block diagram of a vehicle control device 700 based on road section risk detection according to an embodiment of the present disclosure. The vehicle control device 700 based on road section risk detection according to an embodiment of the present disclosure can execute the vehicle control method 100 based on road section risk detection. Figure 7 As shown, the vehicle control device 700 based on road section risk detection may include:

[0261] a risk detection module 701 configured to determine a risk type of a target road segment based on at least one of planned trajectory information of the target road segment to be traversed by the autonomous driving vehicle, predicted trajectory information of obstacle vehicles on the target road segment, and historical vehicle trajectory information of the target road segment;

[0262] The risk processing module 702 is configured to determine a control strategy for the autonomous driving vehicle based on the risk type of the target road segment.

[0263] In some optional implementations, the risk detection module 701 is further configured to:

[0264] Based on the planned trajectory information and the predicted trajectory information, determining whether there is a vehicle conflict area on the target road section;

[0265] In response to a vehicle conflict area existing in the target road section, determining whether the autonomous driving vehicle has a specific driving behavior based on the planned trajectory information;

[0266] In response to the autonomous driving vehicle not having a specific driving behavior, determining that the risk type of the target road segment is a first type of risk;

[0267] In response to the specific driving behavior of the autonomous driving vehicle, the risk type of the target road section is determined to be a second type of risk.

[0268] In some optional implementations, the risk detection module 701 is further configured to:

[0269] Based on the predicted trajectory information and the historical vehicle trajectory information, determining whether the obstructing vehicle has abnormal driving behavior;

[0270] In response to the abnormal driving behavior of the obstacle vehicle, determining that the risk type of the target road section is a third risk type;

[0271] In response to the obstacle vehicle not having abnormal driving behavior, determining whether there is a vehicle conflict area in the target road section based on the planned trajectory information and the predicted trajectory information.

[0272] In some optional implementations, the risk detection module 701 is further configured to:

[0273] In response to the target road section not having a vehicle conflict area, determining whether the target road section has a conflict-prone area based on the historical vehicle trajectory information;

[0274] In response to the presence of a conflict-prone area in the target road section, the risk type of the target road section is determined to be a fourth risk type.

[0275] In some optional implementations, the risk detection module 701 is further configured to:

[0276] determining the curvature of each trajectory point based on the time information and the position information of each trajectory point in the predicted trajectory information;

[0277] Determining a standard score for each trajectory point based on the position information and curvature of each trajectory point;

[0278] Determining whether the standard score of each trajectory point is greater than a preset first threshold;

[0279] In response to a standard score of a trajectory point among the trajectory points being greater than a preset first threshold, it is determined that the autonomous driving vehicle has a specific driving behavior.

[0280] In some optional implementations, the risk detection module 701 is further configured to:

[0281] Clustering the historical vehicle trajectory information to obtain trajectory clusters of the historical vehicle trajectory information;

[0282] Performing kernel density estimation on each of the trajectory clusters to obtain a probability density function of each of the trajectory clusters;

[0283] Determining a probability density value of the predicted trajectory information belonging to each trajectory cluster based on the probability density function of each trajectory cluster and the coordinates of each trajectory point in the predicted trajectory information;

[0284] Determining whether a probability density value of the predicted trajectory information belonging to each trajectory cluster is greater than a preset second threshold;

[0285] In response to the probability density values of the predicted trajectory information belonging to each trajectory cluster being less than or equal to a preset second threshold, it is determined that the obstacle vehicle has abnormal driving behavior.

[0286] In some optional implementations, the risk detection module 701 is further configured to:

[0287] Aligning, segmenting and sampling the historical vehicle trajectory information based on the planned trajectory information;

[0288] Clustering is performed based on the coordinates of the sampling points of each trajectory segment obtained by segmentation to obtain trajectory clusters of the historical vehicle trajectory information.

[0289] In some optional implementations, the risk detection module 701 is further configured to:

[0290] Traverse the number of clusters in the preset set, perform K-means clustering of the corresponding number of clusters based on the coordinates of the sampling points of each trajectory segment obtained by segmentation, and determine the DB index of each trajectory cluster obtained by clustering;

[0291] The DB indices of the K-means clustering of each clustering number are compared, and the trajectory clusters obtained by the K-means clustering of the clustering number with the smallest DB index are used as the trajectory clusters of the historical vehicle trajectory information.

[0292] In some optional implementations, the risk detection module 701 is further configured to:

[0293] Determining the distance between the planned trajectory and the predicted trajectory at the same time based on the coordinates of each trajectory point in the planned trajectory information and the coordinates of each trajectory point in the predicted trajectory information;

[0294] Determine whether the distance between the planned trajectory and the predicted trajectory at the same time is less than the preset safety distance;

[0295] In response to a distance between the planned trajectory and the predicted trajectory at the same time being less than a preset safety distance, it is determined that a vehicle conflict area exists in the target road section.

[0296] In some optional implementations, the risk processing module 702 is further configured to:

[0297] In response to the risk type of the target road segment being the first risk type or the second risk type, determining, based on a preset fuzzy rule and the distance and speed difference between the autonomous driving vehicle and the obstacle vehicle, a membership degree of acceleration, deceleration, and constant speed for the output state of the autonomous driving vehicle;

[0298] Determine a center of gravity value of the membership degree, and adjust a driving speed of the autonomous driving vehicle based on the center of gravity value.

[0299] In some optional implementations, the risk processing module 702 is further configured to:

[0300] In response to the risk type of the target road section being the third type of risk, the autonomous driving vehicle is controlled to slow down and stop based on the current speed of the autonomous driving vehicle, the current speed of the obstacle vehicle, the preset reduction coefficient, the current distance between the autonomous driving vehicle and the obstacle vehicle, and the preset safety distance.

[0301] In some optional implementations, the risk processing module 702 is further configured to:

[0302] In response to the risk type of the target road segment being the fourth risk type, taking the current position of the autonomous driving vehicle as a first point, and determining a first state based on the current speed and acceleration of the autonomous driving vehicle;

[0303] The position of the conflict-prone area closest to the first point is used as a second point, and a second state is determined based on the distance between the conflict-prone area and the first point and a preset speed limit;

[0304] Based on the first state and the second state, a quintic spline curve state transition trajectory and a state transition time from the first point to the second point are determined to control the automatic driving vehicle to travel at a limited speed.

[0305] In addition, an embodiment of the present disclosure also provides an electronic device, which includes at least one processor and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned vehicle control method 100 based on road section risk detection.

[0306] The embodiment of the present disclosure further provides a computer-readable storage medium storing a computer program, which implements the above-mentioned vehicle control method 100 based on road section risk detection when executed by a processor.

[0307] The embodiments of the present disclosure further provide a computer program product, including a computer program, which implements the above-mentioned vehicle control method 100 based on road section risk detection when executed by a processor.

[0308] Figure 8 A block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. Electronic device 800 is intended to represent various forms of digital computers. Electronic device 800 can also represent various forms of mobile devices capable of running computing programs. The components shown herein, their connections and relationships, and their functions are provided for example purposes only and are not intended to limit the implementation of the present disclosure as described and / or claimed herein.

[0309] like Figure 8As shown, electronic device 800 includes a computing unit 810, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 820 or a computer program loaded from a storage unit 880 into a random access memory (RAM) 830. Various programs and data required for the operation of electronic device 800 may also be stored in RAM 830. Computing unit 810, ROM 820, and RAM 830 are connected to each other via a bus 840. An input / output (I / O) interface 850 is also connected to bus 840.

[0310] Multiple components in the electronic device 800 are connected to the I / O interface 850, including an input unit 860, such as a touch screen, etc.; an output unit 870, such as various types of displays, speakers, etc.; a storage unit 880, such as a disk, etc.; and a communication unit 890, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 890 allows the electronic device 800 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0311] The computing unit 810 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the computing unit 810 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 810 executes the various methods and processes described above, such as the vehicle control method 100 based on road segment risk detection. For example, in some embodiments, the vehicle control method 100 based on road segment risk detection can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 880. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 800 via the ROM 820 and / or the communication unit 890. When the computer program is loaded into the RAM 830 and executed by the computing unit 810, one or more steps of the vehicle control method 100 based on road segment risk detection described above can be performed. Alternatively, in other embodiments, the computing unit 810 may be configured to execute the vehicle control method 100 based on road section risk detection in any other appropriate manner (eg, by means of firmware).

[0312] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0313] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0314] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fibers, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0315] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0316] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A vehicle control method based on road section risk detection, characterized in that: include: Determining the risk type of the target road section based on planned trajectory information of the target road section that the autonomous driving vehicle is to traverse, predicted trajectory information of obstacle vehicles on the target road section, and historical vehicle trajectory information of the target road section includes: Based on the planned trajectory information and the predicted trajectory information, determining whether there is a vehicle conflict area on the target road section; In response to a vehicle conflict area existing in the target road section, determining whether the autonomous driving vehicle has a specific driving behavior based on the planned trajectory information; In response to the autonomous driving vehicle not having a specific driving behavior, determining that the risk type of the target road segment is a first type of risk; In response to the autonomous driving vehicle having a specific driving behavior, determining that the risk type of the target road section is a second risk type; Based on the predicted trajectory information and the historical vehicle trajectory information, determining whether the obstructing vehicle has abnormal driving behavior; In response to the abnormal driving behavior of the obstacle vehicle, determining that the risk type of the target road section is a third risk type; Determining a control strategy for the autonomous driving vehicle based on the risk type of the target road section includes: In response to the risk type of the target road segment being the first risk type or the second risk type, determining, based on a preset fuzzy rule and the distance and speed difference between the autonomous driving vehicle and the obstacle vehicle, a membership degree of acceleration, deceleration, and constant speed for the output state of the autonomous driving vehicle; determining a center of gravity value of the degree of membership, and adjusting a driving speed of the autonomous driving vehicle based on the center of gravity value; In response to the risk type of the target road section being the third type of risk, the autonomous driving vehicle is controlled to slow down and stop based on the current speed of the autonomous driving vehicle, the current speed of the obstacle vehicle, the preset reduction coefficient, the current distance between the autonomous driving vehicle and the obstacle vehicle, and the preset safety distance.

2. The method according to claim 1, characterized in that The step of determining the risk type of the target road section based on the planned trajectory information of the target road section to be traversed by the autonomous driving vehicle, the predicted trajectory information of the obstacle vehicle on the target road section, and the historical vehicle trajectory information of the target road section further includes: In response to the target road section not having a vehicle conflict area, determining whether the target road section has a conflict-prone area based on the historical vehicle trajectory information; In response to the presence of a conflict-prone area in the target road section, the risk type of the target road section is determined to be a fourth risk type.

3. The method according to claim 1 or 2, characterized in that The determining, based on the planned trajectory information, whether the autonomous driving vehicle has a specific driving behavior includes: determining the curvature of each trajectory point based on the time information and the position information of each trajectory point in the predicted trajectory information; Determining a standard score for each trajectory point based on the position information and curvature of each trajectory point; Determining whether the standard score of each trajectory point is greater than a preset first threshold; In response to a standard score of a trajectory point among the trajectory points being greater than a preset first threshold, it is determined that the autonomous driving vehicle has a specific driving behavior.

4. The method according to claim 1 or 2, characterized in that The determining, based on the predicted trajectory information and the historical vehicle trajectory information, whether the obstructing vehicle has abnormal driving behavior includes: Clustering the historical vehicle trajectory information to obtain trajectory clusters of the historical vehicle trajectory information; Performing kernel density estimation on each of the trajectory clusters to obtain a probability density function of each of the trajectory clusters; Determining a probability density value of the predicted trajectory information belonging to each trajectory cluster based on the probability density function of each trajectory cluster and the coordinates of each trajectory point in the predicted trajectory information; Determining whether a probability density value of the predicted trajectory information belonging to each trajectory cluster is greater than a preset second threshold; In response to the probability density values of the predicted trajectory information belonging to each trajectory cluster being less than or equal to a preset second threshold, it is determined that the obstacle vehicle has abnormal driving behavior.

5. The method according to claim 4, characterized in that The clustering of the historical vehicle trajectory information to obtain trajectory clusters of the historical vehicle trajectory information includes: Aligning, segmenting and sampling the historical vehicle trajectory information based on the planned trajectory information; Clustering is performed based on the coordinates of the sampling points of each trajectory segment obtained by segmentation to obtain trajectory clusters of the historical vehicle trajectory information.

6. The method according to claim 5, characterized in that Clustering the coordinates of the sampling points of each trajectory segment obtained based on segmentation to obtain trajectory clusters of the historical vehicle trajectory information includes: Traverse the number of clusters in the preset set, perform K-means clustering of the corresponding number of clusters based on the coordinates of the sampling points of each trajectory segment obtained by segmentation, and determine the DB index of each trajectory cluster obtained by clustering; The DB indices of the K-means clustering of each clustering number are compared, and the trajectory clusters obtained by the K-means clustering of the clustering number with the smallest DB index are used as the trajectory clusters of the historical vehicle trajectory information.

7. The method according to claim 1 or 2, characterized in that The determining whether there is a vehicle conflict area on the target road section based on the planned trajectory information and the predicted trajectory information includes: Determining the distance between the planned trajectory and the predicted trajectory at the same time based on the coordinates of each trajectory point in the planned trajectory information and the coordinates of each trajectory point in the predicted trajectory information; Determine whether the distance between the planned trajectory and the predicted trajectory at the same time is less than the preset safety distance; In response to a distance between the planned trajectory and the predicted trajectory at the same time being less than a preset safety distance, it is determined that a vehicle conflict area exists in the target road section.

8. The method according to claim 2, characterized in that The determining of a control strategy for the autonomous driving vehicle based on the risk type of the target road section includes: In response to the risk type of the target road segment being the fourth risk type, taking the current position of the autonomous driving vehicle as a first point, and determining a first state based on the current speed and acceleration of the autonomous driving vehicle; The position of the conflict-prone area closest to the first point is used as a second point, and a second state is determined based on the distance between the conflict-prone area and the first point and a preset speed limit; Based on the first state and the second state, a quintic spline curve state transition trajectory and a state transition time from the first point to the second point are determined to control the automatic driving vehicle to travel at a limited speed.

9. A vehicle control device based on road section risk detection, characterized in that: include: The risk detection module is configured to determine the risk type of the target road section based on the planned trajectory information of the target road section to be traversed by the autonomous driving vehicle, the predicted trajectory information of the obstacle vehicle on the target road section, and the historical vehicle trajectory information of the target road section, including: Based on the planned trajectory information and the predicted trajectory information, determining whether there is a vehicle conflict area on the target road section; In response to a vehicle conflict area existing in the target road section, determining whether the autonomous driving vehicle has a specific driving behavior based on the planned trajectory information; In response to the autonomous driving vehicle not having a specific driving behavior, determining that the risk type of the target road segment is a first type of risk; In response to the autonomous driving vehicle having a specific driving behavior, determining that the risk type of the target road section is a second risk type; Based on the predicted trajectory information and the historical vehicle trajectory information, determining whether the obstructing vehicle has abnormal driving behavior; In response to the abnormal driving behavior of the obstacle vehicle, determining that the risk type of the target road section is a third risk type; A risk processing module is configured to determine a control strategy for the autonomous driving vehicle based on the risk type of the target road segment, including: In response to the risk type of the target road segment being the first risk type or the second risk type, determining, based on a preset fuzzy rule and the distance and speed difference between the autonomous driving vehicle and the obstacle vehicle, a membership degree of acceleration, deceleration, and constant speed for the output state of the autonomous driving vehicle; determining a center of gravity value of the degree of membership, and adjusting a driving speed of the autonomous driving vehicle based on the center of gravity value; In response to the risk type of the target road section being the third type of risk, the autonomous driving vehicle is controlled to slow down and stop based on the current speed of the autonomous driving vehicle, the current speed of the obstacle vehicle, the preset reduction coefficient, the current distance between the autonomous driving vehicle and the obstacle vehicle, and the preset safety distance.

10. An electronic device, characterized in that: include: at least one processor; as well as, A memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the vehicle control method based on road section risk detection as described in any one of claims 1 to 8.

11. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the vehicle control method based on road section risk detection as described in any one of claims 1 to 8 is implemented.

12. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the vehicle control method based on road section risk detection as described in any one of claims 1 to 8 is implemented.

Images